Environment:
	Python: 3.10.11
	PyTorch: 2.0.1
	Torchvision: 0.15.2
	CUDA: 11.7
	CUDNN: 8500
	NumPy: 1.24.3
	PIL: 9.4.0
	Testing environment: [3]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: TerraIncognita
	holdout_fraction: 0.2
	hparams: {
    "resnet18": false,
    "resnet_dropout": 0,
    "nonlinear_classifier": false,
    "data_augmentation": true,
    "clip_backbone": "ViT-B/32",
    "student_model": "resnet",
    "SMA": true,
    "batch_size": 32
}
	hparams_seed: 0
	output_dir: sweep/ablation3/outputs/cc839f842d95b0c5233c3094914f5801
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 36480283
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	trial_seed: 0
	uda_holdout_fraction: 0
	visualize: False
Not saving models
HParams:
	SMA: True
	batch_size: 32
	class_balanced: False
	clip_backbone: ViT-B/32
	data_augmentation: True
	lambda1: 0.5
	lambda2: 0.5
	last_k_epoch: 0.25
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3
	weight_decay: 0.0
	worst_case_p: 0.3333333333333333
using augment transform
using augment transform
using augment transform
using normal transform
using device:  cuda
Using ViT-B/32...
constructing student model
using resnet 50
Using SMA
n_steps 5001
checkpoint_freq 300
agg_test_acc  agg_val_acc   env0_in_acc   env0_out_acc  env1_in_acc   env1_out_acc  env2_in_acc   env2_out_acc  env3_in_acc   env3_out_acc  epoch         loss          mem_gb        step          step_time    
0.0181701266  0.1134353688  0.0503559188  0.0580168776  0.2648607010  0.2722136620  0.0110201511  0.0100755668  0.0184831103  0.0178571429  0.0000000000  4.0746235847  2.3339076042  0             1.4856021404 
0.3849732052  0.7803517796  0.8557869760  0.8533755274  0.8019001155  0.8038007191  0.7248110831  0.6838790932  0.3906947100  0.3792517007  3.0226700252  2.3816509211  2.5991368294  300           0.1598150436 
0.4373617992  0.8331808681  0.9066701819  0.8892405063  0.8476055976  0.8407806882  0.8032115869  0.7695214106  0.4333970682  0.4413265306  6.0453400504  1.9663344312  2.5991368294  600           0.1913278683 
0.4403352798  0.8538734302  0.9216978645  0.9040084388  0.8646809603  0.8515665126  0.8387909320  0.8060453401  0.4418950499  0.4387755102  9.0680100756  1.7819416936  2.5991368294  900           0.1931577897 
0.4400157926  0.8593959623  0.9422620617  0.9071729958  0.8811143921  0.8674884438  0.8573677582  0.8035264484  0.4438070958  0.4362244898  12.090680100  1.6521970356  2.5991368294  1200          0.1899917388 
0.4441609975  0.8780774844  0.9522805167  0.9282700422  0.8903581975  0.8772470467  0.8734256927  0.8287153652  0.4444444444  0.4438775510  15.113350125  1.5273920568  2.5991368294  1500          0.1883784334 
0.4460735854  0.8882450001  0.9596625363  0.9377637131  0.8970342791  0.8957370313  0.8964105793  0.8312342569  0.4465689399  0.4455782313  18.136020151  1.4745176621  2.5991368294  1800          0.1883870586 
0.4399106517  0.8916403637  0.9673081993  0.9419831224  0.9034535884  0.8916281459  0.9105793451  0.8413098237  0.4401954536  0.4396258503  21.158690176  1.4310914453  2.5991368294  2100          0.1887262479 
0.4390603116  0.8972003526  0.9715264962  0.9462025316  0.9133393247  0.8977914741  0.9165617128  0.8476070529  0.4401954536  0.4379251701  24.181360201  1.3932951240  2.5991368294  2400          0.1911409243 
0.4395919774  0.8977381429  0.9717901397  0.9419831224  0.9191167030  0.8998459168  0.9187657431  0.8513853904  0.4395581050  0.4396258503  27.204030226  1.3797909550  2.5991368294  2700          0.1879299792 
0.4404420466  0.9074884922  0.9757447930  0.9504219409  0.9205289511  0.9080636877  0.9250629723  0.8639798489  0.4404079031  0.4404761905  30.226700251  1.3361343978  2.5991368294  3000          0.1895550911 
0.4408669457  0.9075966415  0.9762720801  0.9483122363  0.9291308255  0.9167950693  0.9335642317  0.8576826196  0.4412577013  0.4404761905  33.249370277  1.3113967907  2.5991368294  3300          0.1876531100 
0.4418226976  0.9134760888  0.9794358028  0.9504219409  0.9268198742  0.9121725732  0.9389168766  0.8778337531  0.4440195454  0.4396258503  36.272040302  1.2938105798  2.5991368294  3600          0.1872432494 
0.4422478677  0.9157471712  0.9791721592  0.9588607595  0.9327256387  0.9193631228  0.9392317380  0.8690176322  0.4440195454  0.4404761905  39.294710327  1.1210266213  5.3942589760  3900          0.2045510157 
0.4401222883  0.9158729386  0.9807540206  0.9504219409  0.9320837078  0.9193631228  0.9474181360  0.8778337531  0.4431697472  0.4370748299  42.317380352  0.9254112542  5.3942589760  4200          0.2201828106 
0.4398030721  0.9227703970  0.9825995254  0.9514767932  0.9390165618  0.9188495121  0.9521410579  0.8979848866  0.4442319949  0.4353741497  45.340050377  0.9079364153  5.3942589760  4500          0.2201133982 
0.4408658617  0.9197038892  0.9849723174  0.9578059072  0.9397868789  0.9234720082  0.9559193955  0.8778337531  0.4446568940  0.4370748299  48.362720403  0.9012732093  5.3942589760  4800          0.2215647570 
0.4408658617  0.9260949138  0.9857632481  0.9578059072  0.9414558993  0.9250128403  0.9486775819  0.8954659950  0.4446568940  0.4370748299  50.377833753  0.8979519543  5.3942589760  5000          0.2202491534 
